INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç»ĻæĤ¨

-0.32

åĳ¨è½¬

-0.31

ency

-0.28

WindowTitle

-0.26

 Cous

-0.26

ç½²

-0.25

ooth

-0.25

æľīçĤ¹

-0.25

å¼ĵ

-0.24

å®ŀåľ¨æĺ¯

-0.24

POSITIVE LOGITS

æīĢè°ĵçļĦ

0.28

IA

0.27

 deep

0.25

acias

0.25

ORN

0.24

çļĦä¸ĢéĿ¢

0.24

èĭ¦èĭ¦

0.24

iative

0.24

 pumped

0.24

çĿ¹

0.23

Activations Density 0.002%

of

No Comments

No Known Activations